Abstract: The present disclosure relates to a composition for antiobesity, which contains a Gynostemma pentaphyllum tea or a Gynostemma pentaphyllum tea extract as an active ingredient. The composition of the present disclosure, which contains a Gynostemma pentaphyllum tea or a Gynostemma pentaphyllum tea extract as an active ingredient, is effective for preventing, alleviating or treating diabetes, obesity, muscle loss, etc. since it exhibits the efficacy of increasing AMPK activity, promoting beta oxidation, promoting glucose uptake, etc. In addition, since the composition of the present disclosure is derived from a natural product, it can be safely used as a drug, food, etc. without side effects.

Abstract: An apparatus for determining a vulnerability of a deep learning model according to an embodiment includes a converter configured to generate an input image for the deep learning model by transforming an original image selected from an image dataset, a measurer configured to measure neuron coverage of the deep learning model by inputting the input image into the deep learning model, and an inspector configured to detect, based on a prediction result of the deep learning model for a class of the input image and a class of the original image, an error in the prediction result.

Abstract: An apparatus for determining a vulnerability of a deep learning model according to an embodiment includes a converter configured to generate an input image for the deep learning model by transforming an original image selected from an image dataset, a measurer configured to measure neuron coverage of the deep learning model by inputting the input image into the deep learning model, and an inspector configured to detect, based on a prediction result of the deep learning model for a class of the input image and a class of the original image, an error in the prediction result.

Abstract: An apparatus for fuzzing firmware according to an embodiment includes an emulator that provides a user mode emulation environment for firmware installed in any Internet of Things (IoT) device, a generator that generates one or more test cases in which at least some of a plurality of pre-set mutation operators are applied to at least one of a plurality of seed files, and an executor that executes mutation-based fuzzing on the firmware in the user mode emulation environment based on the one or more test cases.

Abstract: A system for an engine for forecasting cyber threats and a method enabling the forecast of a low-level cyber threat and the forecast of a high-level cyber threat using the low-level cyber threat in a hierarchical structure of cyber threats are provided. The system includes a forecast information database which stores forecast information including cyber threat forecast items, a forecast schedule related to the items, forecast simulation information, forecast item hierarchical structure information, time series data on cyber threats, and sample data on cyber threats; a forecast engine core subsystem which forecasts the levels of threats for the cyber threat forecast items having a hierarchical structure using the forecast information stored in the forecast information database; and a forecast engine control interface which receives control commands for the forecast engine core subsystem from a user or external system, and delivers the received control commands to the forecast engine core subsystem.

Abstract: Provided are a system and method for predicting a cyber threat. The system and method collect various variables and synthetically predict the frequency, dangerousness, possibility, and time of the occurrence of a cyber threat including hacking, a worm/virus, a Denial of Service (DoS) attack, illegal system access, a malicious code, a social engineering attack, system/data falsification, cyber terror/war, weakness exploitation, etc., using a time-series analysis method and a Delphi method, and inform a user in advance of the prediction result, thereby enabling the user to prepare against the cyber threat.

Abstract: A system for an engine for forecasting cyber threats and a method enabling the forecast of a low-level cyber threat and the forecast of a high-level cyber threat using the low-level cyber threat in a hierarchical structure of cyber threats are provided. The system includes a forecast information database which stores forecast information including cyber threat forecast items, a forecast schedule related to the items, forecast simulation information, forecast item hierarchical structure information, time series data on cyber threats, and sample data on cyber threats; a forecast engine core subsystem which forecasts the levels of threats for the cyber threat forecast items having a hierarchical structure using the forecast information stored in the forecast information database; and a forecast engine control interface which receives control commands for the forecast engine core subsystem from a user or external system, and delivers the received control commands to the forecast engine core subsystem.

Abstract: An apparatus and method for detecting anomalous traffic are provided. More particularly, an apparatus and method for detecting anomalous traffic based on entropy of network traffic are provided. The apparatus of detecting anomalous traffic includes: an entropy extraction module for extracting entropy from network traffic; a visualization module for generating an entropy graph based on the entropy; a graph model experience module for updating a graph model for each network attack based on the entropy graph; and an anomalous traffic detection module for detecting anomalous traffic based on the entropy graph and the graph model for each network attack and outputting the detection results to a user. In the apparatus and method, anomalous traffic is detected based on network entropy rather than simple statistics based on the amount of traffic, so that a false alarm rate of the apparatus for detecting anomalous traffic can be reduced.

Abstract: An apparatus and method for detecting anomalous traffic are provided. More particularly, an apparatus and method for detecting anomalous traffic based on entropy of network traffic are provided. The apparatus of detecting anomalous traffic includes: an entropy extraction module for extracting entropy from network traffic; a visualization module for generating an entropy graph based on the entropy; a graph model experience module for updating a graph model for each network attack based on the entropy graph; and an anomalous traffic detection module for detecting anomalous traffic based on the entropy graph and the graph model for each network attack and outputting the detection results to a user. In the apparatus and method, anomalous traffic is detected based on network entropy rather than simple statistics based on the amount of traffic, so that a false alarm rate of the apparatus for detecting anomalous traffic can be reduced.

Abstract: Provided are a system and method for predicting a cyber threat. The system and method collect various variables and synthetically predict the frequency, dangerousness, possibility, and time of the occurrence of a cyber threat including hacking, a worm/virus, a Denial of Service (DoS) attack, illegal system access, a malicious code, a social engineering attack, system/data falsification, cyber terror/war, weakness exploitation, etc., using a time-series analysis method and a Delphi method, and inform a user in advance of the prediction result, thereby enabling the user to prepare against the cyber threat.

Abstract: A multistep integrated security management system and method using an intrusion detection log collection engine and a traffic statistic generation engine is disclosed. An intrusion detection log collection engine capable of collecting logs generated from diverse intrusion detection engines and a traffic statistic generation engine collect and transmit analyzed data to a control intermediate management server. The control intermediate management server performs more accurate intrusion detection by relationally analyzing the intrusion detection log information and the traffic statistic information. A control uppermost management server performs an integrated security management on a large-scale group subject to control by performing an integrated analysis on a large-scale group subject to control, and thus can support the large-scale integrated security management efficiently.